Pruna P Video 2 Serverless API

Pruna's next-gen video model: text, image or audio in, 1080p video with native audio — dialogue, music and SFX — out.

POST /v2/p-video-2 · submit + poll
 1# pip install "segmind>=1.1.0"
 2# export SEGMIND_API_KEY="YOUR_API_KEY"
 3from segmind import SegmindClient, InferenceFailed, InferenceTimeout
 4
 5# Async (v2) — recommended for long-running / video models.
 6# run() blocks up to 600s; submit_async + job.wait(timeout=...) sets a longer
 7# deadline and keeps the request_id so you can re-poll later.
 8client = SegmindClient()                      # reads SEGMIND_API_KEY
 9payload = {
10    "prompt": "A woman walking through a neon-lit Tokyo alley at night, slow tracking shot, rain reflecting the city lights, distant traffic and footsteps on wet pavement",
11    "resolution": "720p",
12    "duration": 5,
13    "aspect_ratio": "16:9",
14    "draft": False,
15    "fps": 24,
16    "save_audio": True,
17    "prompt_upsampling": True,
18    "seed": -1,
19}
20job = client.submit_async("p-video-2", **payload)
21print(job.request_id)                         # available immediately
22try:
23    result = job.wait(timeout=900, interval=2.0)
24    print(result["status"])                  # COMPLETED
25    print(result.get("output"))              # model output (e.g. video URL)
26except InferenceTimeout as e:
27    print("still running:", e.request_id)    # re-poll later with this id
28except InferenceFailed as e:
29    print("failed:", e.detail)
30
31# Fast models (<=600s) can use the one-liner instead:
32# result = segmind.run("p-video-2", **payload)

API Endpoint

POSThttps://api.segmind.com/v1/p-video-2

Parameters

promptrequired
string

Describe the scene, action, camera movement and sound. P Video 2 generates the audio with the video, so dialogue, music and sound effects can be prompted directly.

aspect_ratiooptional
string

Output frame shape. Ignored when an input image is supplied, since the image sets the frame.

Default: "16:9"
Allowed values :
"16:9""9:16""4:3""3:4""3:2""2:3""1:1"
audiooptional
string (uri)

Optional audio track (flac, mp3, wav) to condition the generation. The output matches the audio's length, so the duration setting is ignored when audio is supplied.

draftoptional
boolean

Faster, lower-quality preview for iterating on a prompt. Billed at roughly half the standard per-second rate.

Default: false
durationoptional
integer

Length of the generated video in seconds. Omit this field in an API call to let the model choose the length from your prompt; an audio input overrides it either way.

Default: 5Range: 1 - 20
fpsoptional
integer

Output frame rate. 48 fps gives smoother motion at the same per-second price.

Default: 24
Allowed values :
24 fps24
48 fps48
imageoptional
string (uri)

Optional first-frame image to animate. Supplying one switches the model to image-to-video and overrides the aspect ratio, which is then taken from the image.

last_frame_imageoptional
string (uri)

Optional reference image for the final frame, to steer where the shot ends up.

prompt_upsamplingoptional
boolean

Let the model expand a short prompt into a richer description before generating.

Default: true
resolutionoptional
string

Output resolution. 1080p costs twice as much per second as 720p.

Default: "720p"
Allowed values :
"720p""1080p"
save_audiooptional
boolean

Keep the generated audio track in the returned file. Turn off for a silent video.

Default: true
seedoptional
integer

Fixed seed for reproducible output. Use -1 for a new random result each run.

Default: -1Range: -1 - 2147483647

Response Type

Returns: Video

Asynchronous requests (v2)

Use Async for video, long-running (>~60s), or high-concurrency workloads; Sync is simplest for fast image & LLM calls. Async submits a request and you poll it to completion.

  1. 1
    POST /v2/p-video-2

    Submitreturns request_id, status_url, response_url

  2. 2
    GET /v2/requests/{id}/status

    Polluntil COMPLETED or FAILED

  3. 3
    GET /v2/requests/{id}

    Resultfinal response body

Status states

QUEUEDAccepted, waiting for a worker
PROCESSINGRunning on a worker
COMPLETEDDone — result body is ready
FAILEDErrored (incl. content/RAI blocks)
  • A FAILED request is served as HTTP 422 — the body still carries the error detail.
  • An unknown or expired request_id returns HTTP 404.
  • Results are retained for 1 hour, then expire.
  • Content / RAI blocks surface as FAILED, not a separate state.
  • Track completion by polling the status endpoint.

Common Error Codes

The API returns standard HTTP status codes. Detailed error messages are provided in the response body.

400

Bad Request

Invalid parameters or request format

401

Unauthorized

Missing or invalid API key

403

Forbidden

Insufficient permissions

404

Not Found

Model or endpoint not found

406

Insufficient Credits

Not enough credits to process request

429

Rate Limited

Too many requests

500

Server Error

Internal server error

502

Bad Gateway

Service temporarily unavailable

504

Timeout

Request timed out